Applied / Computing
- Jamas Enright New Zealand Activity Index
- Uli Muellner Connecting research data with stakeholders – the Gambling Data Explorer
- Cory Davis and Luke Symes Using administrative data to better model receipt of transfers
- Michael Eglinton TAWA - Treasury’s microsimulation model of the New Zealand personal tax and transfer system
- Alexander Amies and Jan Schindler Automating national land cover mapping using artificial intelligence
- Anantha Narayanan, Tom Stewart, and Scott Duncan Application of data science methodologies to explore, predict, and model wellbeing outcomes using the New Zealand Integrated Data Infrastructure (IDI).
- Edmond Zhang Smart Search for Electronic Health Records: An NLP-powered approach
- Joel E. Bancolita Exploratory Drivers of Transition as Applied on Workforce Modelling
- Peter Hong Augmented Decisions - even when you don't have all the data!
New Zealand Activity Index
Economic conditions evolve very quickly during crisis periods, and we (the New Zealand government) needed a timely and high-frequency measure of economic conditions to inform policy-making. Gross Domestic Product (GDP) is released quarterly and 10 weeks after the reference quarter. The New Zealand Activity Index (NZAC) was developed by combining eight source indicators and uses principal component analysis to capture as much co-movement of these indicators as possible. This measure is monthly and comes out 2-3 weeks after the end of the month. While not as comprehensive as GDP the NZAC provides a good leading indicator for monthly economic activity.
Connecting research data with stakeholders – the Gambling Data Explorer
The National Gambling Study (NGS) is the first New Zealand population representative longitudinal study into gambling behaviours and attitudes, health, and lifestyles. To support the dissemination and use of the findings from the study the National Gambling Study Explorer provides easy and user-friendly access for stakeholders to information on gambling participation and epidemiological risk factors. The Gambling Data Explorer is freely available at https://www.health.govt.nz/publication/national-gambling-study-data-explorer. This project was delivered for the Ministry of Health in collaboration with AUT. It demonstrates an innovative way to share research findings and data with stakeholders through online dashboards.
Using administrative data to better model receipt of transfers
Microsimulation models such as the New Zealand Treasury’s Tax and Welfare Analysis (TAWA) model play an important role in estimating the impacts of potential policy changes. A challenge facing these models is in estimating the take up of programmes like the Accommodation Supplement (AS). This can lead to significant uncertainty in estimated outcomes, such as fiscal costs and reductions in child poverty. In this presentation the Treasury’s TAWA team outlines work undertaken to better model AS by using administrative data on this programme contained in Stats NZ’s Integrated Data Infrastructure (IDI).
TAWA - Treasury’s microsimulation model of the New Zealand personal tax and transfer system
Tax and Welfare Analysis (TAWA) is the Treasury’s microsimulation model of the New Zealand personal tax and transfer system. The TAWA model uses a combination of survey and administrative data within Stats NZ Integrated Data Infrastructure to model potential policy changes. It is used extensively within Treasury and in external work related to policy analysis of tax and welfare settings.
Automating national land cover mapping using artificial intelligence
Land cover mapping is important for national- and regional-scale policy decision making, and environment and biodiversity monitoring. Previous time steps of Manaaki Whenua’s Land Cover Database (LCDB) have leveraged expert analysis of large volumes of multi-temporal satellite imagery to identify areas of change. This approach traditionally relies on rule-based decision systems in conjunction with time consuming manual data cleaning. We explore the potential of artificial intelligence for developing more flexible, automated processes for land cover classification and change detection. We compare machine learning and object-based methods with image-based convolutional encoder-decoders enabling more fine-grained spatial and temporal predictions.
Anantha Narayanan, Tom Stewart, and Scott Duncan
Auckland University of Technology
Application of data science methodologies to explore, predict, and model wellbeing outcomes using the New Zealand Integrated Data Infrastructure (IDI).
Wellbeing measures currently available in New Zealand are not sensitive enough to capture the effects of policy change – this is partly due to the lack of detailed population-level wellbeing data. Microdata within NZ’s IDI promises to provide a better understanding of wellbeing; however, detailed measures of wellbeing (from the General Social Survey) are only available for a smaller subset of IDI records (i.e., ~8,500 individuals). Extrapolating these wellbeing data to the full IDI population may be possible via advanced data modelling. In this research, we aim to apply machine learning techniques that can predict wellbeing outcomes from IDI administrative data.
Smart Search for Electronic Health Records: An NLP-powered approach
This work looks at how advanced information search software can improve how doctors and nurses find what they need to know from patient electronic records. It is hoped that clinicians can find patient specific information faster, and more comprehensively and accurately. While electronic patient records can keep information in one physical area, this does not necessarily make it easier to find specific information. This is especially so for patients with complicated illnesses, or illnesses that affect many different organs at once. With Smart search clinicians should be more confident that they have found all the information needed for patient care.
Exploratory Drivers of Transition as Applied on Workforce Modelling
Describing factors affecting individuals’ transitions addresses several policy questions. For instance, differentiating retention and exit rates of groups of the workforce based on geography, demography or intervention may inform decision-makers in formulating more targeted policies that can influence funding and the lives of people. We tried developing a framework analysing the drivers of transition in the IDI and employed transition modelling to answer these questions aimed at replicating this to several aspects of people’s lives, such as labour force, education and health. We also employed classification models to address some of limitations, like imputing occupation.
Peter Hong
Houston We Have
Augmented Decisions - even when you don’t have all the data!
Houston We Have uses proprietary software, data, technology and mathematics to help humans make better decisions, especially when most at risk. Sectors where we already develop predictions, forecasts and risk models for enhanced strategic and operational decision making include defence, financial services and fintech, natural resources, and health. Our software, technology and data insight capability can be deployed in any area where better quality, visibility and traceability around decision making is important.